Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    when during input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ด
    0.48
    ซ
    0.47
    น
    0.43
     לי
    0.42
     туда
    0.42
    לי
    0.42
    เรา
    0.41
    Biden
    0.41
    ไ
    0.40
    Jane
    0.39
    POSITIVE LOGITS
     lorsque
    0.45
     during
    0.44
     During
    0.42
     resulting
    0.41
     lors
    0.41
     هنگام
    0.41
     increment
    0.41
     mass
    0.40
     of
    0.40
     when
    0.39
    Act Density 0.051%

    No Known Activations